English

An Integrative Data-Driven Physics-Inspired Approach to Traffic Congestion Control

Systems and Control 2019-12-03 v1 Systems and Control

Abstract

This paper offers an integrative data-driven physics-inspired approach to model and control traffic congestion in a resilient and efficient manner. While existing physics-based approaches commonly assign density and flow traffic states by using the Fundamental Diagram, this paper specifies the flow-density relation using past traffic information recorded in a time sliding window with a constant horizon length. With this approach, traffic coordination trends can be consistently learned and incorporated into traffic planning. This paper also models traffic coordination as a probabilistic process and obtains traffic feasibility conditions using linear temporal logic. Model productive control (MPC) is applied to control traffic congestion through the boundary of the traffic network. Therefore, the optimal boundary inflow is assigned as the solution of a constrained quadratic programming problem.

Keywords

Cite

@article{arxiv.1912.00565,
  title  = {An Integrative Data-Driven Physics-Inspired Approach to Traffic Congestion Control},
  author = {Hossein Rastgoftar and Ella Atkins},
  journal= {arXiv preprint arXiv:1912.00565},
  year   = {2019}
}

Comments

6 pages, 5 figures, submitted to IFAC

R2 v1 2026-06-23T12:32:38.613Z